fineTuneDArch: Fine tuning function for the deep architecture
In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description Usage Arguments Details Value See Also

The fine tuning function for deep architectures. This function use the function saved in the attribute fineTuneFunction to train the deep architecture.

fineTuneDArch(darch, dataSet, dataSetValid = NULL, numEpochs = 1,
  isClass = TRUE, stopErr = -Inf, stopClassErr = 101,
  stopValidErr = -Inf, stopValidClassErr = 101, shuffleTrainData = T,
  debugMode = F, ...)

`darch`	A instance of the class `DArch`.
`dataSet`	`DataSet` containing training and optionally validation and test data.
`dataSetValid`	`DataSet` to be used for validation.
`numEpochs`	The number of training iterations
`isClass`	Indicates whether the training is for a classification net. When `TRUE` then statistics for classification will be determind. Default is `TRUE`
`stopErr`	Stop criteria for the error on the train data. Default is `-Inf`
`stopClassErr`	Stop criteria for the classification error on the train data. Default is `101`
`stopValidErr`	Stop criteria for the error on the validation data. Default is `-Inf`.
`stopValidClassErr`	Stop criteria for the classification error on the validation data. Default is `101`.
`shuffleTrainData`	Whether to shuffle train data before each epoch.
`debugMode`	Whether to enable debug mode, internal parameter.
`...`	Additional parameters for the training function
`bootstrap`	Whether to use bootstrapping to create validation data.

The function trains the given network darch with the function saved in the attribute fineTuneFunction of the DArch-Object. The data and classes for validation and testing are optional. If they are provided the network will be executed with this datasets and statistics will be calculated. This statistics are saved in the stats attribute (see Net). Also it is possible to set stop criteria for the training on the error (stopErr, stopValidErr) or the correct classifications (stopClassErr, stopValidClassErr) of the training or validation dataset.

Trained DArch instance.

DArch, Net, backpropagation, rpropagation, minimizeAutoencoder, minimizeClassifier